Object Detectors Emerge in Deep Scene CNNs — mentioned by jesuslop

Sat, 15 Oct 2016 23:31:49 GMT

In addition to the intro that I liked a lot, I find interesting, or even important, the usage of an unsupervised method to generate the visual symbolic dictionary, a convolutional autoencoder here. In arxiv:1412.6856 unsupervised object detectors emerge as byproducts in a CNN for another kind of task, for more interesting, photorealistic objects.

Paper and discussion history. A mention is not an endorsement.

Object Detectors Emerge in Deep Scene CNNs · HackerPapers discussions

Object Detectors Emerge in Deep Scene CNNs — mentioned by jesuslop